ATLAS OS

ATLAS·OS

Autonomous Teams · Lifecycle · Agents · Skills — Orchestration System

A multi-agent, hook-driven, model-agnostic engineering OS for the terminal.
Hand it a vague idea. Get back a planned, built, tested, committed feature —
with a Greek pantheon of specialist agents doing the work.

Works on macOS, Linux, and Windows through WSL2. Bring Anthropic Claude, OpenAI GPT, OpenRouter, OpenCode Zen, OpenCode Go, or run local Llama / Qwen / DeepSeek models through Ollama, LM Studio, vLLM, or llama.cpp.

Why I Built This ·
How It Compares ·
Install ·
How It Works ·
Dev

Why I Built This

Atlas exists because most AI coding CLIs are either:

- a single chatbot that loses project shape after a few prompts, or
- a process you have to assemble yourself before it can help you ship.

ATLAS·OS keeps the flow simple (atlas, describe the goal, ship) while keeping
the engine serious: multi-agent orchestration, typed tools, hook-based safety,
and persistent project state.

How It Compares

Atlas's edge is not one isolated feature. It is the SDD pipeline, specialist
agents, typed hooks/tools, MCP integration, and release workflow shipped as one
terminal system.

Install

macOS

Linux

Atlas checks npm for newer atlas-os releases when the TUI opens. If your
global install is behind, it shows a short dismissible update notice with:

Windows

WSL2 is recommended for the full Atlas experience.

Then inside Ubuntu:

Native Windows can run the core CLI, but the shell tool expects POSIX commands.
Use WSL2 if you want tool execution to match Linux/macOS behavior.

What Gets Installed

The package installs a small dispatcher plus the native binary for your platform.
Other platform binaries are optional dependencies and are skipped automatically.
If the native binary is unavailable, Atlas…